Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2122 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.5602. Min Act: -0.0001

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.6815. Min Act: -0.0001

Data Index: 26869 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4889. Min Act: -0.0001

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.3994. Min Act: -0.0001

Data Index: 814998 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.2688. Min Act: -0.0001

Data Index: 804459 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4279. Min Act: -0.0001

Data Index: 276590 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4826. Min Act: -0.0001

Data Index: 637011 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.5209. Min Act: -0.0001

Data Index: 1271856 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.3023. Min Act: -0.0001

Data Index: 1034079 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4298. Min Act: -0.0001

Data Index: 78558 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4224. Min Act: -0.0001

Data Index: 771181 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4319. Min Act: -0.0001

Data Index: 467692 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.2641. Min Act: -0.0001

Data Index: 654201 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.2937. Min Act: -0.0001

Data Index: 1237737 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.4119. Min Act: -0.0001

Data Index: 19570 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.2180. Min Act: -0.0001

Data Index: 56319 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.1892. Min Act: -0.0001

Data Index: 919739 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.3115. Min Act: -0.0001

Data Index: 1223960 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.2752. Min Act: -0.0001

Data Index: 181995 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.6815. Min Range: -1.6815

Max Act: 1.2237. Min Act: -0.0001

Data Index: 648960 (C4 (Web Text))

Max Activating Token Index: 374